hooks
Guide to Claude Code hooks — lifecycle events, handler types, decision control, and common patterns. Use when creating, debugging, or planning hooks for guardrails, context injection, quality gates, notifications, or automation.
What this skill does
# Claude Code Hooks
Hooks are deterministic handlers that fire at lifecycle events. Unlike instructions, hooks **cannot be ignored** — they block, inject, or modify at the system level.
## When to Use Hooks vs Other Tools
- **Hooks**: Must happen every time, no exceptions (guardrails, formatting, enforcement)
- **Rules/CLAUDE.md**: Advisory guidance Claude should follow (conventions, preferences)
- **Skills**: On-demand reference material (knowledge, methodology)
## Hook Events
Hooks fire at three points in execution: before the user or agent acts (`UserPromptSubmit`, `PreToolUse`), after the system acts (`PostToolUse`, `Stop`), and during agent lifecycle transitions (`SubagentStart`, `TaskCompleted`). Session bookend events (`SessionStart`, `SessionEnd`) handle setup and teardown. See [reference.md](reference.md) for the full event list with blocking/injection capabilities per event.
## Handler Types
Pick based on how complex the decision is:
| Handler | Use when... |
|---------|-------------|
| **command** | Logic is deterministic — regex check, file exists, env var set. Fastest. |
| **prompt** | Decision requires judgment but no file access — "is this prompt asking for secrets?" |
| **agent** | Decision requires investigation — read files, run commands, check state. |
| **http** | Hook logic lives outside the machine — shared enforcement service, cross-team policy. |
Default to `command`. Escalate to `prompt` only when a shell script can't encode the judgment. Use `agent` sparingly — it spawns a subagent and adds real latency.
## Decision Control
All hook output must be wrapped in `hookSpecificOutput` with the matching `hookEventName`. **`hookEventName` is required** — without it, Claude Code silently drops the payload.
```json
{
"hookSpecificOutput": {
"hookEventName": "PreToolUse",
"additionalContext": "injected text"
}
}
```
See [reference.md](reference.md) for the full per-event return value spec (`permissionDecision`, `updatedInput`, `decision: "block"`, etc.).
## Matchers
Use `|` to target multiple tools: `"matcher": "Write|Edit|MultiEdit"`. MCP tools match as `mcp__servername__toolname`. Omit matcher to catch all tools for that event.
See [reference.md](reference.md) for full matcher syntax including SessionStart variants.
## Skill- and Agent-Scoped Hooks
Hooks can be declared in `SKILL.md` or agent frontmatter to scope them to that skill/agent only — useful for guardrails that shouldn't apply globally. Uses the same matcher/handler format as `hooks.json`, nested under `hooks:` in frontmatter. See [reference.md](reference.md) for a full example.
## Common Patterns
See [patterns.md](patterns.md) for comprehensive examples organized by category:
- Guardrails and enforcement
- Context injection
- Quality gates (auto-format, lint, test)
- Notifications and alerts
- Logging and auditing
- Auto-approval workflows
- Input modification and sandboxing
- Git workflow automation
- Session management
- Agent team coordination
## Best Practices
- **Async for slow operations**: Set `"async": true` for hooks that shouldn't block (tests, notifications)
- **Timeouts**: Default is 60s for sync hooks. Set explicit timeouts for fast hooks.
- **Idempotency**: Hooks may fire multiple times. Guard against duplicate processing.
- **Stop hook loops**: Always check `stop_hook_active` to prevent infinite continuation loops.
- **Minimal hooks.json**: One concern per hook. Compose multiple small hooks rather than one monolith.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.